Multimedia Computing Group, Nanjing University

[CVPR 2022 Oral & TPAMI 2024] MixFormer: End-to-End Tracking with Iterative Mixed Attention

MCG-NJU

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

MCG-NJU

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

MCG-NJU

[CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector

MCG-NJU

[CVPR 2022 Oral & TPAMI 2023] Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion

MCG-NJU

[ECCV 2020] Actions as Moving Points

MCG-NJU

[ICCV 2021] Relaxed Transformer Decoders for Direct Action Proposal Generation

MCG-NJU

[AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

MCG-NJU

[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

MCG-NJU

[ICCV 2021] MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions

MCG-NJU